Numerical Hard SOM with Hardclustering
Default keys path_jar, db_context, and processing_id are described
in Workflow managerc to Scala Engine section page and only the data key is
specific for this payload.
The pipeline description is there, and it also
includes hyperparameters specific keys.
Example of the JSON associate to data key.
JSON template
{
"processingKeyword": "somWithHardclustering",
"customer": "username",
"name": "user defined name of the representation",
"creationTS": 17267393322,
"latestUpdateTS": 17267393344,
"status": 1,
"dataLocations": [
{
"role": "numericaldata",
"dataLocationId": "62bc108b8c51f362811989c8"
}
],
"processingContext": {
"processingName": "user define name, ex SOM",
"editionContext": "user",
"callingContext": "hephIA-solution",
"view": {
"id": "637ce534dd85c10875c4fe26",
"name": "view_11-22-2022_15:05:24"
},
"dataset": {
"name": "my_dataset",
"collection": "datasets"
},
"project": {
"id": 2,
"name": "SOM"
}
},
"hyperParameters": {
"numericalFeatureColumnNames": [
"numericalFeature1",
"numericalFeature2"
],
"maxIterations": 10,
"width": 10,
"length": 10,
"tMin": 0.8,
"tMax": 12.2,
"initializedModel": "dataLocationId if provided, empty String else",
"persistence": "MEMORY_ONLY"
}
}